Abstract: Multi-Objective Particle Swarm Optimizers(MOPSOs) easily converge to a false Pareto front(i. e.，the equivalent of a local optimum in single objective optimization) , and converge slowly. So, we proposed a multi-objective PSO based on adaptive crowding grid(ACG-MOPSO for short). The proposed algorithem has the following characteristic: adaptive crowding grid was used to define the diversity of particles in the external archive to keep the size of the external archive, and the global best particle was assigned by the informations of density and crowding distance to improve the probability of flying to Pareto front Simulation results show that the ACG-MOPSO algorithm is able to find better solutions compared with other algorithms.

Key words: Multi-objective, Particle swarm optimizer, Adaptive crowding grid